ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability
Abstract
Temporal graph neural networks (TGNNs) have gained significant traction for solving real-world temporal graph tasks. However, their interpretability remains limited, as most TGNNs fail to identify which historical interactions most influence a given prediction. Despite promising progress on interpretable TGNNs, existing methods predominantly focus on previously seen historical interactions, which we term stability patterns, while overlooking newly emerging first-time interactions, which we term transition patterns. Both types of patterns are essential for faithful temporal explanations. To address this limitation, we propose ST-TGExplainer, a self-explainable TGNN that disentangles Stability and Transition patterns in temporal graphs for a more faithful Temporal GNN Explainer. Guided by a disentangled information bottleneck objective, ST-TGExplainer learns a compact explanatory subgraph that remains predictive of the event label while explicitly suppressing label-conditioned redundancy between stability and transition patterns. Extensive experiments demonstrate that ST-TGExplainer achieves strong predictive performance and yields more faithful explanations. Code is available at https://github.com/hjchen-hdu/ST-TGExplainer.
Cite
@article{arxiv.2605.19822,
title = {ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability},
author = {Hongjiang Chen and Xin Zheng and Pengfei Jiao and Huan Liu and Zhidong Zhao and Huaming Wu and Feng Xia and Shirui Pan},
journal= {arXiv preprint arXiv:2605.19822},
year = {2026}
}